A California highway crash in Orange County sent unsecured metal pipes through a sedan, narrowly missing the driver, according to California Highway Patrol.

Neural 3D scene representations have shown great potential for 3D reconstruction from 2D images.

This layer contains the information of the background adversarial vehicles whose behaviors are not directly guided by LinguaSim. These vehicles are automatically generated and placed around the ego vehicle and the guided adversarial vehicles by LLM agent Chaos Maker, and roam aimlessly on the given map. The background vehicles significantly increase the uncertainty and complexity of the generated scenarios. B. Adversarial Behavior Generation Compared to other state-of-the-art methods for generating 3D realistic scenarios from natural language descriptions, LinguaSim achieves a higher level of realism, flexibility, and interactivity due to the innovative structure of its Action Generator agent. The detailed workflow of this component will be elaborated further in this section, with a simplified operational logic of the Action Generator illustrated in Figure 1. Figure 1: The basic workflow of module Action Generator To establish a solid foundation for the Action Generator, a retrieval database was constructed to store various behaviors available for the guided adversarial vehicles. Each behavior in the database is referred to as an Atomic Behavior, serving as a fundamental component in the subsequent process. As illustrated in Figure 1, each Atomic Behavior comprises three essential parts: 1) Agent Selection: An autonomous driving agent is selected to guide the adversarial vehicle to which Figure 1: An example of the Behavior T opology W eb generated by the Action Generator the Atomic Behavior is applied. LinguaSim includes various predefined agents, such as the basic CARLA built-in agent that follows a given route, an auto cruise control (ACC) agent that follows the vehicle in front, or the PlanT agent, an imitation-learning-based planning algorithm developed by Renz, Chitta et al. [10]. These agents serve different purposes; for example, the F ollow V ehicle behavior uses the ACC agent, while the PlanT agent is often used for less aggressive behaviors to mimic cautious drivers.

Tesla unveiled more affordable versions of its best-selling Model Y SUV and its Model 3 sedan at $39,990 and $36,990, respectively, as the electric vehicle (EV) manufacturer seeks to reverse falling sales and waning market share amid rising competition. The EV maker announced its new models on Tuesday. Late last year, Musk said the vehicle would be priced below the "key threshold" of $30,000, including US EV tax credits. In the United States, prices effectively rose by $7,500 at the end of last month, when the EV tax credit ended. That helped goose quarterly sales to a record, but expectations are that they will slow down for the rest of the year, unless the affordable car comes to the rescue.

When an entry-level Volvo can get to 60 mph quicker than a Porsche 911, and in the same time as a Ferrari, electric car makers need a reset. It's difficult to imagine it happening now, but cars have in the past seriously triggered politicians. Australia's predilection for big, bluff muscle sedans prompted the so-called " supercar scare " in the early '70s, when various state ministers of transport united in calling for a nationwide ban on what one called "bullets on wheels." Fast forward 20 years and the UK's House of Commons found itself debating the Lotus Carlton, in very many ways the successor to those Antipodean bruisers. An outrageous reimagining of a competent but far from stellar Opel/Vauxhall sedan (it was badged the latter in the UK), the Daily Mail decided the nation's moral well-being was imperiled by its very existence.

Despite significant progress in natural language understanding, Large Language Models (LLMs) remain error-prone when performing logical reasoning, often lacking the robust mental representations that enable human-like comprehension. We introduce a prototype neurosymbolic system, Embodied-LM, that grounds understanding and logical reasoning in schematic representations based on image schemas-recurring patterns derived from sensorimotor experience that structure human cognition. Our system operationalizes the spatial foundations of these cognitive structures using declarative spatial reasoning within Answer Set Programming. Through evaluation on logical deduction problems, we demonstrate that LLMs can be guided to interpret scenarios through embodied cognitive structures, that these structures can be formalized as executable programs, and that the resulting representations support effective logical reasoning with enhanced interpretability. While our current implementation focuses on spatial primitives, it establishes the computational foundation for incorporating more complex and dynamic representations.

Sensor fusion of camera, LiDAR, and 4-dimensional (4D) Radar has brought a significant performance improvement in autonomous driving (AD). However, there still exist fundamental challenges: deeply coupled fusion methods assume continuous sensor availability, making them vulnerable to sensor degradation and failure, whereas sensor-wise cross-attention fusion methods struggle with computational cost and unified feature representation. This paper presents availability-aware sensor fusion (ASF), a novel method that employs unified canonical projection (UCP) to enable consistency in all sensor features for fusion and cross-attention across sensors along patches (CASAP) to enhance robustness of sensor fusion against sensor degradation and failure. As a result, the proposed ASF shows a superior object detection performance to the existing state-of-the-art fusion methods under various weather and sensor degradation (or failure) conditions; Extensive experiments on the K-Radar dataset demonstrate that ASF achieves improvements of 9.7% in AP BEV (87.2%) and 20.1% in AP 3D (73.6%) in object detection at IoU=0.5, while requiring a low computational cost. The code will be available at https://github.com/kaist-avelab/K-Radar.

Earlier this year, Bentley stopped making the W12 that has carried its super-luxury vehicles since 2003, making way for the launch of its V8 hybrid in the new Continental GT. Now comes the second model with this potent combination: the 2025 Flying Spur. It's equipped with the same turbocharged 4.0-liter twin-turbo V8 cranking out 592 horsepower and 590 pound-feet of torque developed in conjunction with Porsche. Paired with a powerful e-motor and a 25.9 kWh battery, total output is an impressive 771 hp and 738 pound-feet of torque. In sum, Bentley calls the Flying Spur the most powerful sedan it has ever built.

Last year, at the IAA show in Berlin, BMW gave us a first look at what it calls the Neue Klasse, a "new class" of sedan that would not only drive BMW into its electric future, but also create a platform with greater efficiency and driving dynamics than we've yet seen from the German brand. Now, the company is showing us an evolution of that concept. A taller one at that, to see just how that same idea for future electrification would apply to an SUV. In keeping with BMW's naming conventions, this one's called the Neue Klasse X. The styling is somewhat predictable in that regard, since it is a taller version of what we saw in the Neue Klasse sedan.

Due to effective pattern mining and feature representation, neural forecasting models based on deep learning have achieved great progress. The premise of effective learning is to collect sufficient data. However, in time series forecasting, it is difficult to obtain enough data, which limits the performance of neural forecasting models. To alleviate the data scarcity limitation, we design Sequence Decomposition Adaptation Network (SeDAN) which is a novel transfer architecture to improve forecasting performance on the target domain by aligning transferable knowledge from cross-domain datasets. Rethinking the transferability of features in time series data, we propose Implicit Contrastive Decomposition to decompose the original features into components including seasonal and trend features, which are easier to transfer. Then we design the corresponding adaptation methods for decomposed features in different domains. Specifically, for seasonal features, we perform joint distribution adaptation and for trend features, we design an Optimal Local Adaptation. We conduct extensive experiments on five benchmark datasets for multivariate time series forecasting. The results demonstrate the effectiveness of our SeDAN. It can provide more efficient and stable knowledge transfer.